© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 91019
    Prev
    Next
    INDEX
    Explanations

    phens

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     referenties
    -0.84
    MigrationBuilder
    -0.77
     Roskov
    -0.74
     Chwiliwch
    -0.73
    AccessorTable
    -0.73
    Tembelea
    -0.72
     MaterialApp
    -0.68
    verwijspagina
    -0.68
     propOrder
    -0.68
    Билгалдахарш
    -0.66
    POSITIVE LOGITS
    HEET
    0.49
    hirts
    0.48
     are
    0.46
     won
    0.46
     considering
    0.45
    ณี
    0.44
     zich
    0.43
     two
    0.43
    hots
    0.43
     were
    0.42
    Activations Density 1.854%

    No Known Activations